Senior Software Developer - Inference Cloud Deployments

yasp is pioneering the future of software development with a compiler that leverages agentic AI for advanced optimization and code generation. As our optimized models move from R&D into the hands of customers, the way we serve them in a fast, reliably, and cost-effectively way which becomes a product in its own right. We are looking for a Software Developer - Inference Cloud Deployments to own how Yasp's models and accelerated workloads are deployed and served in the cloud: the serving infrastructure, the deployment pipelines, and the runtime systems that keep inference performant and dependable under real customer load.

• Build, operate, and scale the cloud infrastructure that serves yasp's optimized inference workloads across high-performance hardware (GPGPU / NPU / TPU) and multiple cloud targets.

• Design and maintain deployment pipelines that take models and compiled artifacts from R&D into production, with repeatable releases, rollbacks, and environment parity.

• Optimize the serving path for latency, throughput, and cost through dynamic batching, autoscaling, resource scheduling, and capacity planning across GPU fleets.

• Instrument inference services with monitoring, alerting, and observability; own reliability, on-call health, and incident response for the systems you ship.

• Collaborate with R&D, Platform, and customer-facing teams to productionize new model and optimization work, and to fold deployment realities back into how those systems are built.

• Write clean, tested, production-level code and tooling, and share what you learn to raise the bar across the engineering team.

• Degree in Software Engineering, Computer Science, or a related field, or equivalent experience.

• 5+ years of Python development experience on Linux and distributed systems.

• Strong understanding of containerization, CI, and Kubernetes.

• Proven history of operating services in production with ownership of subsystems, on-call, and the discipline that comes with it.

• Hands-on experience deploying workloads to a major cloud platform (AWS, Azure, or Google Cloud).

• System thinker with an eye on code quality, testability, and operational cost.

• Excellent problem-solving and communication skills, and a collaborative, team-oriented mindset.

Preferred:

• Experience with model-serving frameworks and runtimes (e.g., Triton Inference Server, vLLM, TGI, TensorRT-LLM, KServe, or Ray Serve).

• Familiarity with GPU infrastructure: drivers, scheduling, multi-tenant sharing, and fleet utilization.

• Experience optimizing inference economics — autoscaling, spot/preemptible capacity, and cost-per-request tuning.

• Familiarity with popular ML frameworks (e.g., PyTorch, TensorFlow) and inference formats (ONNX, TensorRT).

• Strong observability practice (metrics, tracing, structured logging) for latency-sensitive services.

• Hot sauce lover.

• Competitive salary.

• Comprehensive health benefits (including dental).

• Opportunities for professional development and growth.

• Flexible work hours.

• Dynamic and collaborative work environment.

• Cutting-edge software and hardware platforms.

Ready to apply? Submit your application through this posting and our team will review it personally. From there, you can expect a short intro call, a technical evaluation built around real problems, and conversations with the people you'd work with directly.